mlsanityData to 7 Oct 2026

Transferable Sparse Adversarial Attack

arXiv 2105.14727 ↗First posted 31 May 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the ℓ0 norm constraint, which can succeed by only modifying a few pixels of an image. Despite a high attack success rate, prior sparse attack methods achieve a low transferability under the black-box protocol due to overfitting the target model. Therefore, we introduce a generator architecture to alleviate the overfitting issue and thus efficiently craft transferable sparse adversarial examples. Specifically, the generator decouples the sparse perturbation into amplitude and position components. We carefully design a random quantization operator to optimize these two components jointly in an end-to-end way. The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods. Moreover, our method achieves superior inference speed, 700× faster than other optimization-based methods. The code is available at https://github.com/shaguopohuaizhe/TSAA.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

36 of 46 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
24 more
  1. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  4. 2017One pixel attack for fooling deep neural networkscited by 579
  5. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  6. 2017Adversarial Patchcited by 514
  7. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  8. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  9. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  10. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  11. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  12. 2017Generative Adversarial Perturbationscited by 153
  13. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  14. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  15. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  16. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  17. 2018SparseFool: a few pixels make a big differencecited by 94
  18. 2019Cross-Domain Transferability of Adversarial Perturbationscited by 92
  19. 2020GeoDA: a geometric framework for black-box adversarial attackscited by 66
  20. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  21. 2017Adversarial Transformation Networks: Learning to Generate Adversarial Examplescited by 60
  22. 2020GreedyFool: Distortion-Aware Sparse Adversarial Attackcited by 37
  23. 2018Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressionscited by 31
  24. 2018An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networkscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 2; 2025: 0; 2026: 1.

9 papers.

  1. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
  2. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  3. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  4. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  5. 2022SAIF: Sparse Adversarial and Imperceptible Attack Frameworkcited by 1
  6. 2024Sparse and Transferable Universal Singular Vectors Attackcited by 1
  7. 2024STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognitioncited by 1
  8. 2023Towards Generic and Controllable Attacks Against Object Detectioncited by 0
  9. 2026Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attackscited by 0